Upload ml_debug_env_grpo_fixed.ipynb

Upload BLOG.md

Update README.md

Update README.md

Upload BLOG.md

exclude images from hf space

track pngs with lfs

add demo and reward curve images

fix: one-liner curl commands for Windows CMD

fix: module-level session store for cross-instance state

fix: stateless demo using /grader endpoint

fix: single worker to preserve session state

add images, update readme, fix gitignore

interactive demo landing page with curl commands

permanently remove images from HF Space tracking

fix grader: other type penalty, gradient_not_zeroed loss check

fix image url

remove images from HF Space, add to gitignore

update README with story arc, partial obs, 8 tasks, training results

add GRPO training notebook

fix landing page route to /ui

add landing page, blog link, HF Space UI

Block A B C: partial observability, LLM judge, adversarial scheduler

v3: compound tasks, hardened graders, other type, 8 tasks total

expand README with layman explanations and full file docs

update README for 6 tasks

remove hardcoded api key

add 6 tasks, fix log format, multi-turn retry, grader improvements

fix: scores strictly between 0 and 1 exclusive

fix: inference.py calls LLM proxy directly

fix: use injected API_KEY and API_BASE_URL

add Dockerfile to root for HF Space

fix: 20/20 all tasks 1.0

fix: use API_BASE_URL and API_KEY env vars for LLM proxy

fix: self-contained inference.py, no network dependency

fix: emit [START]/[STEP]/[END] structured output for Phase 2 validator

Fix inference.py to hit deployed HF Space baseline endpoint

Add inference.py for hackathon checker

Add gitignore

ML Debug Environment - OpenEnv Hackathon submission